Fast nearest neighbor search with distance bounds

Student: Igoshin Andrey

Supervisor: Mikhail Vladimirovich Batsyn

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Data Mining (Master)

Year of Graduation: 2020

Today, computer vision technologies are becoming more and more in demand. One of the tasks of computer vision is the task of identifying a person, as, for example, in Apple’s FaceID technology. This work is devoted to the development of an algorithm that allows you to speed up the identification algorithm. The paper proposes an approach that involves clustering a database of photographs followed by a search in these clusters in the given order. Two algorithms are proposed in the work: one using K-Means for clustering, and the other using VAE (Variational Auto Encoder). Two varieties of the brute force algorithm are also implemented. Comparison by perfomance of the four algorithms is also made. According to the results of comparison, these two algorithms really surpass the brute force algorithms in perfomance.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses